---
id: daily-run
name: "run"
url: https://skills.yangsir.net/skill/daily-run
author: alirezarezvani
domain: science
tags: ["experiment-tracking", "scientific-method", "research-methodology", "automation", "iterative-testing"]
install_count: 1200
rating: 4.30 (20 reviews)
github: https://github.com/alirezarezvani/claude-skills
---

# run

> 执行单次实验迭代：回顾历史、决定变更、编辑代码、提交并评估结果，支持科学方法的系统化实验流程

**Stats**: 1,200 installs · 4.3/5 (20 reviews)

## Before / After 对比

### 实验迭代自动化

**Before**:

手动记录实验历史、分析结果、设计下次实验、修改代码并运行验证，实验流程混乱，难以追踪变量影响，结果不可复现

**After**:

自动管理实验历史和上下文，系统化执行实验迭代全流程，每次变更都被记录和评估，确保实验结果可追溯和可复现

| Metric | Before | After | Change |
|---|---|---|---|
| 实验迭代时间 | 60分钟 | 15分钟 | -75% |

## Readme

# run

# /ar:run — Single Experiment Iteration

Run exactly ONE experiment iteration: review history, decide a change, edit, commit, evaluate.

## Usage

```
/ar:run engineering/api-speed              # Run one iteration
/ar:run                                     # List experiments, let user pick

```

## What It Does

### Step 1: Resolve experiment

If no experiment specified, run `python {skill_path}/scripts/setup_experiment.py --list` and ask the user to pick.

### Step 2: Load context

```
# Read experiment config
cat .autoresearch/{domain}/{name}/config.cfg

# Read strategy and constraints
cat .autoresearch/{domain}/{name}/program.md

# Read experiment history
cat .autoresearch/{domain}/{name}/results.tsv

# Checkout the experiment branch
git checkout autoresearch/{domain}/{name}

```

### Step 3: Decide what to try

Review results.tsv:

- What changes were kept? What pattern do they share?

- What was discarded? Avoid repeating those approaches.

- What crashed? Understand why.

- How many runs so far? (Escalate strategy accordingly)

**Strategy escalation:**

- Runs 1-5: Low-hanging fruit (obvious improvements)

- Runs 6-15: Systematic exploration (vary one parameter)

- Runs 16-30: Structural changes (algorithm swaps)

- Runs 30+: Radical experiments (completely different approaches)

### Step 4: Make ONE change

Edit only the target file specified in config.cfg. Change one thing. Keep it simple.

### Step 5: Commit and evaluate

```
git add {target}
git commit -m "experiment: {short description of what changed}"

python {skill_path}/scripts/run_experiment.py \
  --experiment {domain}/{name} --single

```

### Step 6: Report result

Read the script output. Tell the user:

- **KEEP**: "Improvement! {metric}: {value} ({delta} from previous best)"

- **DISCARD**: "No improvement. {metric}: {value} vs best {best}. Reverted."

- **CRASH**: "Evaluation failed: {reason}. Reverted."

### Step 7: Self-improvement check

After every 10th experiment (check results.tsv line count), update the Strategy section of program.md with patterns learned.

## Rules

- ONE change per iteration. Don't change 5 things at once.

- NEVER modify the evaluator (evaluate.py). It's ground truth.

- Simplicity wins. Equal performance with simpler code is an improvement.

- No new dependencies.

Weekly Installs448Repository[alirezarezvani/…e-skills](https://github.com/alirezarezvani/claude-skills)GitHub Stars10.1KFirst SeenMar 13, 2026Security Audits[Gen Agent Trust HubWarn](/alirezarezvani/claude-skills/run/security/agent-trust-hub)[SocketPass](/alirezarezvani/claude-skills/run/security/socket)[SnykPass](/alirezarezvani/claude-skills/run/security/snyk)Installed onopencode423codex422cursor422gemini-cli421github-copilot421amp420

---
*Source: https://skills.yangsir.net/skill/daily-run*
*Markdown mirror: https://skills.yangsir.net/api/skill/daily-run/markdown*